【第8篇】M2Det

QijieZhao1, TaoSheng1, YongtaoWang1∗, ZhiTang1, YingChen2, LingCai2 and HaibinLing3

1 Institute of Computer Science and Technology, Peking University, Beijing, P.R. China

2 AI Labs, DAMO Academy, Alibaba Group

3 Computer and Information Sciences Department, Temple University {zhaoqijie, shengtao, wyt, tangzhi}@pku.edu.cn, {cailing.cl, chenying.ailab}@alibaba-inc.com, {hbling}@temple.edu

Abstract: Feature pyramids are widely exploited by both the state-of the-art one-stage object detectors (e.g., DSSD, RetinaNet, RefineDet) and the two-stage object detectors (e.g., Mask RCNN, DetNet) to alleviate the problem arising from scale variation across object instances. Although these object detectors with feature pyramids achieve encouraging results, they have some limitations due to that they only simply construct the feature pyramid according to the inherent multiscale, pyramidal architecture of the backbones which are originally

文章来源: wanghao.blog.csdn.net，作者：AI浩，版权归原作者所有，如需转载，请联系作者。

原文链接：wanghao.blog.csdn.net/article/details/105593927